Research on Automatic Detection Method of Railway Fastener Defects Based on Image Processing
Science Discovery
Volume 7, Issue 6, December 2019, Pages: 429-435
Received: Nov. 3, 2019; Published: Dec. 12, 2019
Views 314      Downloads 66
Authors
Qiu Yijin, School of Urban Rail Transportation, Shanghai University of Engineering Science, Shanghai, China
Lv Zhaomin, School of Urban Rail Transportation, Shanghai University of Engineering Science, Shanghai, China
Article Tools
Follow on us
Abstract
With the rapid development of rail transit, the detection requirements for the various components of the track line are getting higher and higher, and relying on manual detection has the disadvantages of high cost and low efficiency. Therefore, it is urgent to study the method of automatic detection of track lines.This paper is based on the development history of computer vision and deep learning detection algorithm in fastener detection. It mainly introduces the related algorithms of positioning and classification, including the "cross" and template matching positioning algorithm; extracting the image direction gradient histogram The graph and the local binary pattern feature are merged, and the algorithm is classified by the support vector machine. At the same time, the convolutional neural network Alexnet architecture is used to extract the generalization characteristics of the fasteners to improve the classification accuracy of the fasteners. Finally, the problems and dilemmas of the existing fastener detection algorithms are discussed.
Keywords
Fastener Positioning, Fastener Classification, Deep Learning, Fastener Detect
To cite this article
Qiu Yijin, Lv Zhaomin, Research on Automatic Detection Method of Railway Fastener Defects Based on Image Processing, Science Discovery. Vol. 7, No. 6, 2019, pp. 429-435. doi: 10.11648/j.sd.20190706.19
Copyright
Copyright © 2019 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
ADDRESS
Science Publishing Group
1 Rockefeller Plaza,
10th and 11th Floors,
New York, NY 10020
U.S.A.
Tel: (001)347-983-5186